{"id":"PYSEC-2026-1565","summary":"RunGptLLM class in LlamaIndex has a command injection","details":"A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.","aliases":["CVE-2024-4181","GHSA-pw38-xv9x-h8ch","PYSEC-2024-324"],"modified":"2026-07-13T07:26:21.243502373Z","published":"2026-07-07T11:45:42.603795Z","references":[{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2024-4181"},{"type":"WEB","url":"https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"},{"type":"PACKAGE","url":"https://github.com/run-llama/llama_index"},{"type":"WEB","url":"https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"},{"type":"PACKAGE","url":"https://pypi.org/project/llama-index-llms-rungpt"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-pw38-xv9x-h8ch"}],"affected":[{"package":{"name":"llama-index-llms-rungpt","ecosystem":"PyPI","purl":"pkg:pypi/llama-index-llms-rungpt"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.1.3"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2"],"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/llama-index-llms-rungpt/PYSEC-2026-1565.yaml"}}],"schema_version":"1.7.5","severity":[{"type":"CVSS_V3","score":"CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"}]}